v0.1.1 Free & open source · macOS · Windows · Linux

Every meeting. Every word. Never leaves your machine.

Local Transcriber records your calls, transcribes them with whisper.cpp or Parakeet on your own GPU, and turns them into summaries your team can use. No account. No cloud. No uploads.

Download for free Watch the 15s tour
Works offlineRecording never depends on AIMIT licensed
Two separate tracksMe · Others — no diarization needed
Vulkan GPU activewhisper.cpp · large-v3-turbo
Published to GitLab wikimeetings/q3-roadmap-sync

Built on proven open source

Showreel

Fifteen seconds. The whole workflow.

How it works

Record first. Transcribe when you're ready.

Recording and transcription are separate on purpose. Your audio is saved the moment it's captured — AI is an optional second step that can never damage the original.

01 — RECORD

Capture both sides

Microphone, device audio, or both at once as two separate tracks. 5-second chunks hit the disk as you talk, so a crash can't eat your meeting.

02 — TRANSCRIBE

Native, GPU-fast

One click runs whisper.cpp or Parakeet locally, with live progress, cancel and retry. Language is auto-detected. Nothing is uploaded.

03 — SHARE

Summarize & ship

A local LLM writes the summary and key points. Push it to a GitLab wiki, book the follow-up in your calendar, or export TXT, Markdown and JSON.

Features

Everything a meeting needs. Nothing it doesn't.

A desktop app built on Tauri and Rust — small, fast and native on every platform.

Two-way capture for online calls

Your mic and the call audio are recorded as two independent tracks, so every line is labeled Me or Others — speaker labels without diarization guesswork.

One-click GPU

Vulkan and CUDA acceleration through voxtype. Metal on Apple Silicon.

gpu: active · vulkan

Crash-safe by design

Audio streams to disk in small chunks. Power cut? Reopen and hit Recover.

Tiered model catalog

Models ranked S–D by accuracy. Pick, download, done.

Sparakeet-tdt-0.6b-v3best
Alarge-v3-turbodefault
Bsmall.enfast

Full-text search

Find that one sentence across every meeting.

…lock the Q3 roadmap before Friday.
…roadmap review moved to Thursday.

Summaries from a local LLM

Use Ollama or an OpenCode agent on your machine, or point it at any OpenAI-compatible endpoint you choose.

Summary ollama · llama3.1
The team agreed to lock the Q3 roadmap by Friday; GitLab export ships next sprint.
  • Roadmap locked by Friday
  • Follow-up call Thursday 14:00

Your company calendar

CalDAV, Microsoft Graph and Exchange EWS. See recordings next to real events and create follow-ups straight from a summary.

Team sharing without a backend

Publish transcripts and summaries to a GitLab wiki, issue or repository folder. Access follows project membership — there's no server of ours in between.

📄 Wiki page🗂 meetings/<slug>/transcript.md🐞 Issue

Open formats, real files

Every finished meeting is mirrored to ~/Documents/Local Transcribe. Export anywhere, anytime.

transcript.txttranscript.mdtranscript.jsonme.webmothers.webmmeeting.json
Privacy

Private by architecture, not by promise.

There's no account and no server to trust. Here is exactly what can leave your machine — and when.

Your audioRecorded, stored and transcribed locally.
NEVER LEAVES
Transcripts & summariesLocal by default — with Ollama, even the AI runs on-device.
STAYS LOCAL
Analytics & telemetryNone. Not anonymous, not opt-out. None.
NONE
GitLab, calendar, remote LLMOnly if you turn them on, only to endpoints you configure.
YOUR CHOICE
0accounts0servers of ours0bytes of audio uploaded
Download

Get Local Transcriber for your platform.

Click download, open it, record. Transcription is built in — free, MIT-licensed, no sign-up.

v0.1.1Latest release

Nothing else to install

Download, open, record. No account, no setup wizard, no command line.

Transcription built in

whisper.cpp ships inside the app. The speech model downloads once, on your first transcription.

Verify your download

Every binary lists its SHA-256. Compare with shasum -a 256 <file>.

All binaries & versions

Every build for every platform, straight from GitHub Releases.

Build from source

Node 20+, Rust and the Tauri prerequisites for your OS.

build.sh
$ git clone https://github.com/GrzeskoByte/local-transcript
$ cd local-transcript
$ npm install --ignore-scripts
$ npm run tauri:build
# installers → src-tauri/target/release/bundle/
gpu-engine.sh (optional)
# Optional: bring your own GPU engine (used automatically)
# Linux — voxtype with Vulkan/CUDA
$ sudo voxtype setup gpu --enable
# Windows — a CUDA/Vulkan whisper.cpp build
> setx WHISPER_CLI_PATH C:\whisper\whisper-cli.exe
FAQ

Questions, answered.

Does my audio ever get uploaded?

No. Recording, storage and transcription all happen on your computer. The only features that send anything over the network are ones you switch on yourself — GitLab sharing, calendar sync or a remote LLM — and they send text, never audio.

Do I need to install anything else?

No. The transcription engine (whisper.cpp) ships inside the app. The first time you click Transcribe, it downloads its speech model once (about 550 MB) with a progress bar — after that everything works offline. Power users can plug in their own GPU engine (voxtype or a whisper.cpp build) and the app will use it automatically.

Do I need an internet connection?

Only to download the app and the speech model once. After that, recording, transcription and local summaries work fully offline.

Which speech model should I use?

Start with large-v3-turbo — it's the default and a great balance of speed and accuracy. For the best accuracy, parakeet-tdt-0.6b-v3 sits at the top of the S-tier; on Linux it needs voxtype's ONNX variant. Settings ranks every model so the choice is obvious.

Can it record Zoom, Meet or Teams calls?

Yes — choose Mic + Device and share the call's tab or window when asked. Your voice and the call are saved as separate tracks. Device-audio availability depends on your OS, and headphones are recommended so the mic doesn't pick up the speakers.

What happens if transcription fails?

Nothing bad. The recording is the source of truth and is never modified by transcription. You'll see "Your original recording is still safe." and a Retry button.

macOS says the app can't be opened — what now?

Early builds may not be notarized yet. Right-click the app in Applications and choose Open, or run xattr -dr com.apple.quarantine "/Applications/Local Transcribe.app".

Is it really free?

Yes. Local Transcriber is open source under the MIT license. No tiers, no trial, no account.

Your meetings. Your machine.

Record. Transcribe. Summarize. Privately.

Download for free Star on GitHub